Institute of Mathematics and Informatics Bulgarian Academy of Sciences, Association for the Development of the Information Society
Proceedings of the National Conference on "Education and Research in the Information Society", Plovdiv, June, 2018, 186p-195p
With the rapid development of information technology and the expansion of the
Internet, social network users and bloggers generate a huge amount of emotionally rich text.
The automatic classification of emotions in the text is an area of interest to both social sciences
and applications, such as the discovery of attitudes towards a given product. This paper
presents and explores the machine learning methods used to classify emotions in the text. A
comparative study of the effectiveness of the classification of the main methods of solving this
task has been made. It also presents results from a study of correlations between the main
types of emotions in the text.
Report published in the Proceedings of the National Conference on "Education and Research in the Information Society", Plovdiv, June, 2018